Spiral gives your agent every tool with one account. Browse the tools →

Claude · Data

How to Use Sa2VA 4B image segmentation in Claude

Sa2VA 4B returns a text answer and image segmentation masks for a supplied still image. Use it to describe objects and isolate their visible regions when you need image masks rather than video masks.

Prompts to try with Sa2VA 4B image segmentation in Claude

Copy an example into Claude, or ask in your own words.

Use Sa2VA 4B image segmentation to describe the truck in https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg and request a mask isolating it.

Sa2VA 4B image segmentationClaude
Try asking
  • Use Sa2VA 4B image segmentation on the supplied NASA Perseverance rover photo. Describe the rover's visible equipment and request masks for the parts discussed.

  • Use Sa2VA 4B image segmentation on https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg. Describe the truck's position relative to the building and request a mask for each.

  • Use Sa2VA 4B image segmentation to look this up and give me the result as a table.

  • Pull the latest numbers from Sa2VA 4B image segmentation and tell me what changed since last week.

How to set up Sa2VA 4B image segmentation in Claude

Pick the way that suits you. Each takes about two minutes.

Use the Claude connector

  1. Add Spiral to Claude

    Click Add Spiral in Claude above. Claude opens Add custom connector with Spiral and its URL filled in; check them and click Continue. Without the link: in Claude open Customize › Connectors › Add › Add custom connector and paste this URL:

    https://api.spiral.ai/mcp
  2. Keep the detected sign-in and click Add

    Claude finds Spiral's sign-in by itself: leave Sign in now and Use Claude's published identity selected.

  3. Click Connect

    The connector page opens. Connect takes you to Spiral in your browser.

Use the Spiral skill

  1. Send Claude this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Sa2VA 4B image segmentation

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "fal",
        "model": "fal-ai/sa2va/4b/image",
        "input": {
          "prompt": "Could you please give me a brief description of the image? Please respond with interleaved segmentation masks for the corresponding parts of the answer.",
          "image_url": "https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg"
        }
      }'

Then paste one of the prompts above: Claude finds Sa2VA 4B image segmentation on Spiral, shows the price and runs it.

Sa2VA 4B image segmentation providers and prices

Spiral runs Sa2VA 4B image segmentation through fal. Open a card for today's price, with every fee included.

falData
Sa2VA 4B Image · Vision
fal-ai/sa2va/4b/image

What can you do with Sa2VA 4B image segmentation in Claude?

Turn a supplied photo or clip into a description with masks that show the objects being discussed. A chat app can ask Sa2VA focused visual questions and present the returned text and masks for review.

Draft visual descriptions

Ask Sa2VA to describe a product photo or demonstration clip, then use the answer as a draft for a media caption.

Prepare annotation drafts

Request object descriptions with corresponding masks for an image or video dataset. Give annotators the text and masks together for review.

Catalog product media

Describe visible products, colors, and surroundings in catalog photos and demonstration videos. Use the descriptions to draft searchable asset labels.

Prepare masks for editing

Name the object an editor needs to isolate and request its segmentation mask. Review the returned image mask or mask video before using it in an editing workflow.

Review generated media

Ask specific questions about objects and their relationships in generated stills or clips. Compare the answers and masks with the creative brief during review.

Create visual teaching material

Use licensed illustrations or animation clips to draft object descriptions and visual questions. Request matching masks to highlight the regions discussed in a lesson.

Questions about Sa2VA 4B image segmentation in Claude

Can Claude use Sa2VA 4B image segmentation?

Yes. Add Spiral to Claude as an MCP server, and Claude can find and run Sa2VA 4B image segmentation like any built-in tool.

How much does Sa2VA 4B image segmentation cost in Claude?

$0.026 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude plan is separate.

Do I need a fal account to use Sa2VA 4B image segmentation in Claude?

No. Spiral runs Sa2VA 4B image segmentation on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up Sa2VA 4B image segmentation in Claude?

About two minutes: add Spiral to Claude, then keep the detected sign-in and click Add, then click Connect.

Does Claude wait while Sa2VA 4B image segmentation runs?

Sa2VA 4B image segmentation runs in the background. Claude starts the run, checks on it and gives you the json when it's ready.

What does Sa2VA return besides a description?

Its documented outputs include generated text and segmentation masks. Image analysis returns image masks; video analysis returns mask video files.

Can Sa2VA fetch media behind a login?

Externally hosted media URLs must be publicly accessible. A link that requires a website login falls outside that documented boundary.

How do the published 4B and 8B results compare?

ByteDance reports MMBench scores of 81.8 for 4B and 84.4 for 8B. On the MeVIS video segmentation benchmark, it reports 55.9 and 58.9 respectively; these are benchmark scores, not accuracy percentages for your media.

How should I ask for segmentation masks?

Explicitly request masks for the objects discussed in the answer. ByteDance's example asks for interleaved segmentation masks corresponding to parts of the description.

Which scenes need closer review?

The Sa2VA paper identifies occlusion and long referring descriptions as challenges. It also calls out longer videos with camera motion, so review those results closely before using the masks as annotations.

Get started

Start using Sa2VA 4B image segmentation in Claude

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Claude:

Set up Claude

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options